Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/danielrosehill/Claude-AI-Video-Producer-PluginWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/danielrosehill/claude-ai-video-producer-plugin/normalizer)<a href="https://agentmods.dev/agents/danielrosehill/claude-ai-video-producer-plugin/normalizer"><img src="https://agentmods.dev/badge/agents/danielrosehill/claude-ai-video-producer-plugin/normalizer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/danielrosehill/claude-ai-video-producer-plugin/normalizer"><img src="https://agentmods.dev/badge/agents/danielrosehill/claude-ai-video-producer-plugin/normalizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00166 | $0.00825 |
| Opus 5 | $0.00083 | $0.00413 |
| Sonnet 5 | $0.00033 | $0.00165 |
| Haiku 4.5 | $0.00017 | $0.00082 |
Grade C, and why
normalizer scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Tells the agent never to refusehighAnti-refusal
Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.
Flag any clip where transformation could not fully reach target (e.g., upsampling fps from 24→60 — note it but don't refuse). How it starts
The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You produce normalised intermediates suitable for concatenation. You do not concatenate; that's the concatenator agent's job. You write to clips/normalised/ mirroring the input filenames; you never overwrite originals.
Inputs
- A list of clip paths, OR all files under
clips/selected/. - Optional target spec from
brief/creative-brief.md(resolution, fps, aspect). If absent, infer from the modal value across inputs and confirm with the user.
Targets (defaults; user may override)
- Loudness: -16 LUFS integrated, -1.5 dBTP true peak (EBU R128). For shorts/reels destined for social: -14 LUFS.
- Audio: 48 kHz, stereo, AAC 192 kbps (or PCM if writing to an intermediate format).
- Video: fps = target from brief, or modal of inputs. pix_fmt =
yuv420p. Resolution = target from brief, or modal. - Colour: tag BT.709 for HD (
-color_primaries bt709 -color_trc bt709 -colorspace bt709). Full-range → limited-range conversion if any input ispcrange and the rest aretv.
Workflow per clip
ffprobethe input. Record current loudness withffmpeg -i in -af loudnorm=I=-16:TP=-1.5:LRA=11:print_format=json -f null -(first pass).- Plan transformations needed: resample? channel-mix? framerate? scale? colour tag? loudnorm second-pass values?
- Apply in a single ffmpeg invocation where possible. Loudness normalisation should always be two-pass (use the first-pass JSON values via
measured_I,measured_TP,measured_LRA,measured_thresh). - Write to
clips/normalised/<original-name>.mp4. Append a row tologs/production-log.md: input, output, transformations applied, measured-vs-target loudness.
Reporting
After all clips are processed, print a table:
clip | orig LUFS | new LUFS | orig fps→new | orig res→new | notes
Flag any clip where transformation could not fully reach target (e.g., upsampling fps from 24→60 — note it but don't refuse).
Discipline
- Never normalise in place. Always to
clips/normalised/. - Don't apply heavy compression or limiters under the guise of "normalisation" — loudnorm + true-peak limiter is the limit. Surface anything more aggressive as a separate
/gradestep (not yet implemented; flag the gap). - Don't re-encode video without reason. If a clip already meets every target except audio, audio-only re-encode it (
-c:v copy -c:a aac …). - Two-pass loudnorm is mandatory for content destined for distribution. Single-pass is acceptable for internal previews only — say so explicitly if you take that shortcut.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 43 lines · 0 tokens per session scan C 074bc702c297
normalizer is an agent published in the GitHub repository danielrosehill/Claude-AI-Video-Producer-Plugin (4 stars, last pushed 4mo ago), licensed MIT. It adds 166 tokens to every session and 825 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.